A Collaborative Safety Shield for Safe and Efficient CAV Lane Changes in Congested On-Ramp Merging

2026-02-10

AI Summary

This work addresses the challenge of balancing safety and efficiency in lane-changing decisions for connected and autonomous vehicles (CAVs) in dense traffic scenarios. The authors propose a Multi-Agent Safety Shield (MASS) framework that, for the first time, integrates Control Barrier Functions (CBFs) with Multi-Agent Reinforcement Learning (MARL) to develop a collaborative lane-changing controller, termed MARL-MASS. By modeling inter-vehicle interactions through a graph structure, the approach formulates a unified optimization objective and a tailored reward function that jointly enforce safety constraints and promote cooperative efficiency. Simulation results in congested on-ramp merging scenarios demonstrate that MARL-MASS rigorously satisfies safety requirements, significantly improves traffic throughput, and enhances the stability of policy training.

Technology Category

• Multiagent Systems: Multiagent Learning
• Natural Language Processing: Safety and Robustness
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Lane changing in dense traffic is a significant challenge for Connected and Autonomous Vehicles (CAVs). Existing lane change controllers primarily either ensure safety or collaboratively improve traffic efficiency, but do not consider these conflicting objectives together. To address this, we propose the Multi-Agent Safety Shield (MASS), designed using Control Barrier Functions (CBFs) to enable safe and collaborative lane changes. The MASS enables collaboration by capturing multi-agent interactions among CAVs through interaction topologies constructed as a graph using a simple algorithm. Further, a state-of-the-art Multi-Agent Reinforcement Learning (MARL) lane change controller is extended by integrating MASS to ensure safety and defining a customised reward function to prioritise efficiency improvements. As a result, we propose a lane change controller, known as MARL-MASS, and evaluate it in a congested on-ramp merging simulation. The results demonstrate that MASS enables collaborative lane changes with safety guarantees by strictly respecting the safety constraints. Moreover, the proposed custom reward function improves the stability of MARL policies trained with a safety shield. Overall, by encouraging the exploration of a collaborative lane change policy while respecting safety constraints, MARL-MASS effectively balances the trade-off between ensuring safety and improving traffic efficiency in congested traffic. The code for MARL-MASS is available with an open-source licence at https://github.com/hkbharath/MARL-MASS

Problem

• lane change
• Connected and Autonomous Vehicles
• safety
• traffic efficiency
• congested on-ramp merging

Innovation

• Control Barrier Functions
• Multi-Agent Reinforcement Learning
• Collaborative Lane Changing
• Safety Shield
• Connected and Autonomous Vehicles